Increase mining productivity, optimise ore fragmentation and boost performance

Design for Outcome (DfO) applies machine learning to in-field measurement sensor data and block model data. The resulting predictive algorithm is then applied to new data sets to automatically generate blastability domains. Loading rules are then configured relative to the domains to produce tailored hole-by-hole blast designs.

Mining Mag Award 2021 badge

Industry

  • Iron Ore
  • Surface Metal

Features and Benefits

IronOre_ReduceDrillAndBlastCost_Widget1

Utilisation of MWD data in blasting workflow

 

SurfaceMetal_HotAndOrReactiveGround_widget2

Tailored blast designs that match energy to domains

SurfaceCoal_DraglineDozerProductivity_Widget4

Outcome driven blasting

Quarrying_ReduceDrillandBlastCost_Widget1

Efficient generation of tailored blast designs

SurfaceMetal_ReduceDrillAndBlastCost_Widget4

Orebody knowledge to tailored blasting application

Resources

Conference Paper - Applying Machine Learning to Drill and Blast Optimisation (pdf 1.1MB)

Conference Paper - This paper describes a Design for Outcome case study at Roy Hill Iron Ore Mine, Western Australia.

Orica acknowledges the 26th World Mining Congress as the publisher of the conference proceedings.

Download now

Link through to Conference Paper - Applying Machine Learning to Drill and Blast Optimisation (pdf 1.1MB)

High Resolution Rock Domaining Based on Drilling and Blast Data and Machine- Learning Technology (pdf 1MB)

Conference Paper - This paper describes a Design for Outcome case study at an open put copper mine in Chile.

Orica acknowledges the 26th World Mining Congress as the publisher of the conference proceedings.

Download now

Link through to High Resolution Rock Domaining Based on Drilling and Blast Data and Machine- Learning Technology (pdf 1MB)

Contact

*Mandatory fields

 

Mandatory field(s) marked with *
  • Design for Outcome